Leaky RNNs improve grid-cell-like representations and path-integration accuracy by acting as a low-pass filter that stabilizes dynamics against noise.
Speed cells in the medial entorhinal cortex.Nature, 523(7561):419–424
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
NEAT-NC feeds navigation-cell-like inputs into the NEAT algorithm to evolve recurrent networks that improve robot path planning performance in static and dynamic environments.
citing papers explorer
-
Impact of leaky dynamics on predictive path integration accuracy in recurrent neural networks
Leaky RNNs improve grid-cell-like representations and path-integration accuracy by acting as a low-pass filter that stabilizes dynamics against noise.
-
NEAT-NC: NEAT guided Navigation Cells for Robot Path Planning
NEAT-NC feeds navigation-cell-like inputs into the NEAT algorithm to evolve recurrent networks that improve robot path planning performance in static and dynamic environments.